Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for solving linear discrimination vector in matrix rank spaces of between-class scatter and total scattering

A linear identification and classification technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of difficulty in searching all the best identification vectors, and achieve the effect of improving the identification ability and eliminating redundancy.

Active Publication Date: 2013-05-08
NANJING CHINA SPACENET SATELLITE TELECOM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a linear discriminant feature extraction method for the defect that it is difficult to search for all the best discriminant vectors in the existing linear discriminant feature extraction technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for solving linear discrimination vector in matrix rank spaces of between-class scatter and total scattering
  • Method for solving linear discrimination vector in matrix rank spaces of between-class scatter and total scattering
  • Method for solving linear discrimination vector in matrix rank spaces of between-class scatter and total scattering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] The public AT&T standard face image database is used. The AT&T library includes 40 face categories, and each face category has 10 face images with different facial poses, expressions and facial details, and the image size is 112×92.

[0038] Data preprocessing: downsampling the 112×92 image matrix to a size of 28×23. Straighten by row into a 644-dimensional column vector, and normalize the pixel values ​​​​of the image between 0-1. Each type of face sample is randomly divided into two parts, one part is used as a training sample and the other part is used as a test sample.

[0039] There are samples of C=40 categories, and the number of training samples of the i-th category is N i , N i The value range is N i =2,3,4,5,6,7,8,9, where i=1,2...,40, the total number of samples is First construct matrices A, B and D:

[0040] Construct a matrix A with N rows and N-1 columns as

[0041] A = - ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for solving a linear discrimination vector in matrix rank spaces of a between-class scatter and total scattering. The method comprises the following steps: constructing three matrixes by utilizing a training sample and type information thereof; calculating a new matrix by utilizing the constructed three matrixes and a sample matrix; orthogonalizing the column vector of the new matrix to acquire an mutually orthogonal discrimination vector; projecting a sample characteristic and a characteristic to be identified to the calculated linear discrimination vector inan identifying phase to acquire an optimal discrimination characteristic; and calculating the distance between the characteristic to be identified and the sample characteristic, and classifying the sample to be identified to the face type corresponding to the minimum distance. The linear discrimination vector is uncorrelated to the characteristics, so as to eliminate redundancy among linear discrimination characteristics and improve the discriminating capability of the discrimination characteristic.

Description

technical field [0001] The invention relates to a method for solving a linear discriminant vector in the inter-class divergence and total divergence matrix rank space, in particular to a linear discriminant feature extraction and identification method for high-dimensional samples under small sample conditions. The invention can be used in the fields of machine learning and pattern recognition, and can be used for feature extraction and recognition of various high-dimensional data under the condition of small samples. Background technique [0002] Feature extraction technology is an important content in pattern recognition, and it can usually be divided into two categories: supervised and unsupervised feature extraction. Unsupervised feature extraction methods can be divided into principal component analysis and independent component analysis. Since the category information of the training samples is not used, it is difficult to obtain useful discriminant features for classif...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
Inventor 贺云辉
Owner NANJING CHINA SPACENET SATELLITE TELECOM